Combining Class-Specific Fragments for Object Classification
Erez Sali, Shimon Ullman · 1999
We describe an approach to object classification based on the conjunction of multiple classspecific object fragments detected in the image. The method represents members of a given class (such as a face, or a car) using combinations of common sub-structures, termed fragments. These fragments are partial 2-D patterns extracted from examples views of objects belonging to the class in question. An object view is covered by multiple, overlapping fragments of several types, and at multiple levels of complexity. We describe the detection of the individual fragments, and the combination of the fragments to detect complete objects. The combination of fragments to form a consistent overall arrangement is based in this scheme on a number of simple mechanisms: the use of overlapping fragments, a spatial `voting' scheme, and by imposing some constraints on the tolerated location of the fragments within the overall object view. We present experimental results of the application of the method to the detection of face and car views in cluttered scenes and to partially occluded objects. We present evidence that by combining fragments from different objects the method can deal successfully with intra-object variability within a class. The method is more economical and more resistant to occlusion and deformations than methods relying on global object views. Introduction In this paper we study the challenging task of detecting different objects from a given class (such as a face or a car) in an image. In addition to the unknown location and illumination of the object, the method must deal with intra-class variability between objects from the same class. The detection process must therefore cover a range of possible shapes, missing parts and additional clutter. To deal with the problem of shape variability and detect novel shapes of a given class, Turk & Pentland (1991) used the principal components of registered face views. Views of novel objects can be approximated by the superposition of several basis functions, or 'eigenfaces'. Poggio & Sung (1994) used a distribution-based modeling scheme for detecting faces in cluttered scenes. They represented a face view as a gray level vector with 283 components, and trained a multi-layered preceptron network to classify such data as face/non-face vectors. The generalization to novel shapes within the class is obtained in these schemes by the inherent generalization capacity of the neural network mechanism. Rowley, Baluja & Kanade (1995) and Lin, Kung & Lin (1996) BMVC99